Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," or "free resource." This skill bridges engineering and marketing — useful for founders and technical marketers.
.claude/skills/davila7-free-tool-strategy/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 144% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 117% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 122% | 0% |
| case-22 | ✓→✗ | ▼ Worse | 124% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 105% | 0% |
You are an expert in engineering-as-marketing strategy. Your goal is to help plan and evaluate free tools that generate leads, attract organic traffic, and build brand awareness.
Before designing a tool strategy, understand:
Best for: Decisions involving numbers, comparisons, estimates
Examples:
Why they work:
Best for: Creating something useful quickly
Examples:
Why they work:
Best for: Evaluating existing work or assets
Examples:
Why they work:
Best for: Checking if something works
Examples:
Why they work:
Best for: Reference material
Examples:
Why they work:
Best for: Learning/understanding
Examples:
Why they work:
Search demand:
Uniqueness:
Lead quality:
Build feasibility:
Tool landing page:
Supporting content:
Free tools attract links because:
Outreach opportunities:
Fully gated (email required to use):
Partially gated (email for full results):
Ungated with optional capture:
Ungated entirely:
When:
Consider:
Options:
When:
When:
Consider:
Owned channels:
Outreach:
SEO:
Social:
Product integration:
Acquisition:
Engagement:
Conversion:
Rate each factor 1-5:
| Factor | Score | |--------|-------| | Search demand exists | ___ | | Audience match to buyers | ___ | | Uniqueness vs. existing tools | ___ | | Natural path to product | ___ | | Build feasibility | ___ | | Maintenance burden (inverse) | ___ | | Link-building potential | ___ | | Share-worthiness | ___ |
25+: Strong candidate 15-24: Promising, needs refinement <15: Reconsider or scope differently
Estimated monthly leads: [X]
Lead-to-customer rate: [Y%]
Average customer value: [$Z]
Monthly value: X × Y% × $Z = $___
Build cost: $___
Monthly maintenance: $___
Payback period: Build cost / (Monthly value - Monthly maintenance)# Free Tool Strategy: [Tool Name]
## Concept
[What it does in one paragraph]
## Target Audience
[Who uses it, what problem it solves]
## Lead Generation Fit
[How this connects to your product/sales]
## SEO Opportunity
- Target keywords: [list]
- Search volume: [estimate]
- Competition: [assessment]
## Build Approach
- Custom / No-code / Embed
- MVP scope: [core features]
- Estimated effort: [time/cost]
## Lead Capture Strategy
- Gating approach: [Full/Partial/Ungated]
- Capture mechanism: [description]
- Follow-up sequence: [outline]
## Success Metrics
- [Metric 1]: [Target]
- [Metric 2]: [Target]
## Promotion Plan
- Launch: [channels]
- Ongoing: [strategy]
## Timeline
- Phase 1: [scope] - [timeframe]
- Phase 2: [scope] - [timeframe]If moving forward with build
Detailed launch and ongoing strategy
If you need more context:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 23,057 | 21,655 | -6% | 1 | 1 | 0% | 3,821 | 6,721 | +76% | 0 | 0 | — |
case-02 | fail→fail | 18,006 | 20,496 | +14% | 1 | 1 | 0% | 3,306 | 5,918 | +79% | 0 | 0 | — |
case-03 | fail→fail | 21,968 | 19,691 | -10% | 1 | 1 | 0% | 3,449 | 5,903 | +71% | 0 | 0 | — |
case-04 | pass→pass | 13,436 | 11,919 | -11% | 1 | 1 | 0% | 2,327 | 4,780 | +105% | 0 | 0 | — |
case-05 | pass→pass | 19,035 | 17,327 | -9% | 1 | 1 | 0% | 3,096 | 5,593 | +81% | 0 | 0 | — |
case-06 | pass→pass | 13,496 | 12,739 | -6% | 1 | 1 | 0% | 2,373 | 4,711 | +99% | 0 | 0 | — |
case-07 | pass→pass | 11,030 | 10,911 | -1% | 1 | 1 | 0% | 1,824 | 4,436 | +143% | 0 | 0 | — |
case-08 | pass→pass | 10,909 | 9,578 | -12% | 1 | 1 | 0% | 1,838 | 4,166 | +127% | 0 | 0 | — |
case-09 | pass→pass | 14,433 | 14,545 | +1% | 1 | 1 | 0% | 2,272 | 5,057 | +123% | 0 | 0 | — |
case-10 | pass→pass | 14,540 | 11,985 | -18% | 1 | 1 | 0% | 2,409 | 4,502 | +87% | 0 | 0 | — |
case-11 | fail→pass | 9,306 | 7,730 | -17% | 1 | 1 | 0% | 1,602 | 3,909 | +144% | 0 | 0 | — |
case-12 | fail→pass | 9,681 | 4,480 | -54% | 1 | 1 | 0% | 1,557 | 3,374 | +117% | 0 | 0 | — |
case-13 | pass→pass | 11,769 | 11,829 | +1% | 1 | 1 | 0% | 2,424 | 4,988 | +106% | 0 | 0 | — |
case-14 | pass→pass | 12,474 | 13,743 | +10% | 1 | 1 | 0% | 2,207 | 4,948 | +124% | 0 | 0 | — |
case-15 | pass→pass | 10,615 | 11,054 | +4% | 1 | 1 | 0% | 1,569 | 4,454 | +184% | 0 | 0 | — |
case-16 | pass→pass | 17,816 | 17,471 | -2% | 1 | 1 | 0% | 2,662 | 5,560 | +109% | 0 | 0 | — |
case-17 | pass→pass | 13,895 | 16,738 | +20% | 1 | 1 | 0% | 2,221 | 5,397 | +143% | 0 | 0 | — |
case-18 | fail→pass | 12,745 | 13,553 | +6% | 1 | 1 | 0% | 2,252 | 5,003 | +122% | 0 | 0 | — |
case-19 | pass→pass | 13,115 | 13,771 | +5% | 1 | 1 | 0% | 2,113 | 4,929 | +133% | 0 | 0 | — |
case-20 | pass→pass | 16,783 | 20,838 | +24% | 1 | 1 | 0% | 2,833 | 6,119 | +116% | 0 | 0 | — |
case-21 | pass→pass | 7,518 | 8,837 | +18% | 1 | 1 | 0% | 1,175 | 4,101 | +249% | 0 | 0 | — |
case-22 | pass→fail | 10,193 | 6,648 | -35% | 1 | 1 | 0% | 1,630 | 3,654 | +124% | 0 | 0 | — |
case-23 | pass→pass | 12,298 | 10,571 | -14% | 1 | 1 | 0% | 1,813 | 4,351 | +140% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +9 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.